The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local TypeScript scripts (scripts/main.ts and scripts/chunk.ts) using the bun runtime to perform markdown processing and chunking. This involves local file system access to read source documents and write translated segments.
[EXTERNAL_DOWNLOADS]: The workflow involves fetching content from user-provided URLs to materialize them into local markdown files for translation.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes untrusted content from external files, URLs, and text inputs.
Ingestion points: Source content is ingested from file paths, external URLs, or inline text as described in the materialization step of the workflow.
Boundary markers: The prompt templates provided in references/subagent-prompt-template.md do not utilize explicit delimiters or 'ignore' instructions for the source content being translated.
Capability inventory: The skill can execute shell commands via bun, write files to the project and user home directories, and perform network requests to fetch source material.
Sanitization: No sanitization or validation of the input content is performed before it is analyzed or translated by the LLM.

baoyu-translate